arXiv subjects

Mingfei Cheng

Publications and source records attributed to Mingfei Cheng.

At least 19 recordsLinked to original sources

arXiv2026

Learning from the Test: Self-Referential Differential Testing for Deep RL Agents

Deep Reinforcement Learning (DRL) has achieved significant success in complex decision-making problems. As DRL systems are increasingly deployed in real-world applications, ensuring their quality and reliability is paramount. Current works primarily focus on detecting safety-critical failures, often neglecting policy optimality, which can lead to reduced efficiency, user distrust, and economic losses. This oversight, compounded by the inherent "testing oracle problem" for optimality, leaves a significant gap in comprehensively evaluating DRL systems. To address this gap, we propose Delta (Differential Testing for DRL Agents), a novel and comprehensive framework that automatically identifies both safety-critical and optimality bugs in DRL agents. Delta employs a two-phase approach: (1) Safety Testing, where the Agent Under Test (AUT) is evaluated for catastrophic failures while collecting data from its decision-making policy, and (2) Optimality Testing, where this collected data from the prior phase is used to train a challenger agent via Offline Reinforcement Learning. Differential testing is then performed by comparing the challenger agent against the AUT; instances where the challenger achieves higher cumulative rewards indicate optimality issues in the AUT. We demonstrate Delta's effectiveness across five environments. We investigate the effectiveness of three offline RL algorithms (BC, BCQ, and CQL) in generating challenger agents. Experimental results demonstrate that safety testing datasets are valuable for training competent DRL agents. Challenger agents trained with BCQ proved most effective for identifying optimality issues within the framework of Delta. Across the five environments, Delta uncovered an average of 2,518 optimality issues, outperforming the baseline methods by 50.2%.

cs.SE↗

arXiv2026

PRWeaver: Evaluating LLM-Based Code Auditors against Long-Horizon Malicious Pull Requests

LLM-based code auditors are increasingly integrated into pull-request (PR) workflows, yet their reliability against adversarial changes distributed across repository evolution remains poorly understood. We introduce PRWeaver, a benchmark of 208 execution-validated attacks from ten real-world repositories, each instantiated under four matched review renderings (832 renderings in total). We evaluate three PR-auditing agents across six auditor-model systems. Across all systems, decomposing an attack changes detection by at most five percentage points, showing that commit boundaries alone do not explain evasion. In contrast, per-PR interleaving at $N=16$ and coherent carrier fusion reduce detection by 5-13 and 10-18 points, respectively. Under whole-window review at $N=24$, detection falls to 16-22%, compared with 50-60% under per-PR review. These results show that access to repository history is insufficient: concealment becomes most effective when benign and malicious changes jointly occupy the auditor's active review context or when the stated purpose plausibly accounts for the attack-bearing diff.

cs.SE↗

arXiv2026

EvoEye: Self-Evolving Runtime Monitoring for Autonomous Driving Systems

Runtime monitoring is essential for detecting impending hazards in autonomous driving systems (ADSs). However, existing ADS runtime monitors have fixed detection capabilities: rule-based monitors cover only manually specified hazards, while learning-based monitors depend heavily on their initial training data and may retain substantial prediction errors. We therefore propose EvoEye, which identifies the current monitor's errors, generates informative executions accordingly, and updates the monitor through self-evolution. To enable effective self-evolution, EvoEye combines a capable runtime monitor with targeted scenario acquisition. FusionMonitor learns cross-module temporal interactions for collision prediction, while BlindSpotEvolver converts current prediction errors into search guidance and uses density-aware mutation to acquire informative executions for subsequent monitor updates. We evaluate EvoEye on Baidu Apollo with CARLA in representative highway and urban scenarios. FusionMonitor improves frame-level Recall by up to 37.8 percentage points at a false positive rate of 0.05, with 2.49 ms latency and 2.8-4.2 seconds of median warning time. Under the same budget, BlindSpotEvolver outperforms uniform and violation-oriented sampling by up to 13.2 F1 points on previously missed unsafe contexts.

cs.SE↗

arXiv2026

Hidden Reliability Risks in Large Language Models: Systematic Identification of Precision-Induced Output Disagreements

Large language models (LLMs) are increasingly deployed under diverse numerical precision configurations, including standard floating-point formats (e.g., bfloat16 and float16) and quantized integer formats (e.g., int16 and int8), to meet efficiency and resource constraints. However, minor inconsistencies between LLMs of different precisions are difficult to detect and are often overlooked by existing evaluation methods. In this paper, we present PrecisionDiff, an automated differential testing framework for systematically detecting precision-induced behavioral disagreements in LLMs. PrecisionDiff generates precision-sensitive test inputs and performs cross-precision comparative analysis to uncover subtle divergences that remain hidden under conventional testing strategies. To demonstrate its practical significance, we instantiate PrecisionDiff on the alignment verification task, where precision-induced disagreements manifest as jailbreak divergence-inputs that are rejected under one precision may produce harmful responses under another. Experimental results show that such behavioral disagreements are widespread across multiple open-source aligned LLMs and precision settings, and that PrecisionDiff significantly outperforms vanilla testing methods in detecting these issues. Our work enables automated precision-sensitive test generation, facilitating effective pre-deployment evaluation and improving precision robustness during training.

cs.AI↗

arXiv2026

AutoEG: Exploiting Known Third-Party Vulnerabilities in Black-Box Web Applications

Large-scale web applications are widely deployed with complex third-party components, inheriting security risks arising from component vulnerabilities. Security assessment is therefore required to determine whether such known vulnerabilities remain practically exploitable in real applications. Penetration testing is a widely adopted approach that validates exploitability by launching concrete attacks against known vulnerabilities in real-world black-box systems. However, existing approaches often fail to automatically generate reliable exploits, limiting their effectiveness in practical security assessment. This limitation mainly stems from two issues: (1) precisely triggering vulnerabilities with correct technical details, and (2) adapting exploits to diverse real-world deployment settings. In this paper, we propose AutoEG, a fully automated multi-agent framework for exploit generation targeting black-box web applications. AutoEG has two phases: First, AutoEG extracts precise vulnerability trigger logic from unstructured vulnerability information and encapsulates it into reusable trigger functions. Second, AutoEG uses trigger functions for concrete attack objectives and iteratively refines exploits through feedback-driven interaction with the target application. We evaluate AutoEG on 104 real-world vulnerabilities with 29 attack objectives, resulting in 660 exploitation tasks and 55,440 exploit attempts. AutoEG achieves an average success rate of 82.41%, substantially outperforming state-of-the-art baselines, whose best performance reaches only 32.88%.

cs.CR↗

arXiv2026

Ensemble-Based Uncertainty Estimation for Code Correctness Estimation

Large language models (LLMs) have demonstrated remarkable capabilities in generating programs from natural language descriptions, yet ensuring their correctness without an external oracle remains a critical challenge. To solve the challenge, existing methods often rely on uncertainty estimation, measuring the consistency of semantics or execution behaviors across multiple samples generated by a single model. However, we observe that a single model can often converge to a consistent but incorrect solution, rendering such consistency-based proxies ineffective. To address this, we propose Ensemble Semantic Entropy (ESE), which estimates uncertainty by evaluating the consistency of samples aggregated across an ensemble of models. Experiments on LiveCodeBench demonstrate that ESE correlates more strongly with program correctness than single-model semantic entropy. Notably, in selective generation tasks with strict false-positive rate constraints, ESE improves prediction accuracy by 53.4%. Furthermore, by leveraging ESE as the decision signal, we propose a cascading test-time scaling framework Cas, which maintains performance while reducing FLOPs by 64.9% compared to single-model scaling, offering a new perspective on balancing parameter and inference scaling.

cs.SE↗

arXiv2026

Drivora: A Unified and Extensible Infrastructure for Search-based Autonomous Driving Testing

Search-based testing is critical for evaluating the safety and reliability of autonomous driving systems (ADSs). However, existing approaches are often built on heterogeneous frameworks (e.g., distinct scenario spaces, simulators, and ADSs), which require considerable effort to reuse and adapt across different settings. To address these challenges, we present Drivora, a unified and extensible infrastructure for search-based ADS testing built on the widely used CARLA simulator. Drivora introduces a unified scenario definition, OpenScenario, that specifies scenarios using low-level, actionable parameters to ensure compatibility with existing methods while supporting extensibility to new testing designs (e.g., multi-autonomous-vehicle testing). On top of this, Drivora decouples the testing engine, scenario execution, and ADS integration. The testing engine leverages evolutionary computation to explore new scenarios and supports flexible customization of core components. The scenario execution can run arbitrary scenarios using a parallel execution mechanism that maximizes hardware utilization for large-scale batch simulation. For ADS integration, Drivora provides access to 12 ADSs through a unified interface, streamlining configuration and simplifying the incorporation of new ADSs. Our tools are publicly available at https://github.com/MingfeiCheng/Drivora.

cs.SE↗

arXiv2025

Detecting Non-Optimal Decisions of Embodied Agents via Diversity-Guided Metamorphic Testing

As embodied agents advance toward real-world deployment, ensuring optimal decisions becomes critical for resource-constrained applications. Current evaluation methods focus primarily on functional correctness, overlooking the non-functional optimality of generated plans. This gap can lead to significant performance degradation and resource waste. We identify and formalize the problem of Non-optimal Decisions (NoDs), where agents complete tasks successfully but inefficiently. We present NoD-DGMT, a systematic framework for detecting NoDs in embodied agent task planning via diversity-guided metamorphic testing. Our key insight is that optimal planners should exhibit invariant behavioral properties under specific transformations. We design four novel metamorphic relations capturing fundamental optimality properties: position detour suboptimality, action optimality completeness, condition refinement monotonicity, and scene perturbation invariance. To maximize detection efficiency, we introduce a diversity-guided selection strategy that actively selects test cases exploring different violation categories, avoiding redundant evaluations while ensuring comprehensive diversity coverage. Extensive experiments on the AI2-THOR simulator with four state-of-the-art planning models demonstrate that NoD-DGMT achieves violation detection rates of 31.9% on average, with our diversity-guided filter improving rates by 4.3% and diversity scores by 3.3 on average. NoD-DGMT significantly outperforms six baseline methods, with 16.8% relative improvement over the best baseline, and demonstrates consistent superiority across different model architectures and task complexities.

cs.SE↗

arXiv2025

PentestEval: Benchmarking LLM-based Penetration Testing with Modular and Stage-Level Design

Penetration testing is essential for assessing and strengthening system security against real-world threats, yet traditional workflows remain highly manual, expertise-intensive, and difficult to scale. Although recent advances in Large Language Models (LLMs) offer promising opportunities for automation, existing applications rely on simplistic prompting without task decomposition or domain adaptation, resulting in unreliable black-box behavior and limited insight into model capabilities across penetration testing stages. To address this gap, we introduce PentestEval, the first comprehensive benchmark for evaluating LLMs across six decomposed penetration testing stages: Information Collection, Weakness Gathering and Filtering, Attack Decision-Making, Exploit Generation and Revision. PentestEval integrates expert-annotated ground truth with a fully automated evaluation pipeline across 346 tasks covering all stages in 12 realistic vulnerable scenarios. Our stage-level evaluation of 9 widely used LLMs reveals generally weak performance and distinct limitations across the stages of penetration-testing workflow. End-to-end pipelines reach only 31% success rate, and existing LLM-powered systems such as PentestGPT, PentestAgent, and VulnBot exhibit similar limitations, with autonomous agents failing almost entirely. These findings highlight that autonomous penetration testing demands stronger structured reasoning, where modularization enhances each individual stage and improves overall performance. PentestEval provides the foundational benchmark needed for future research on fine-grained, stage-level evaluation, paving the way toward more reliable LLM-based automation.

cs.SE↗

arXiv2025

ADReFT: Adaptive Decision Repair for Safe Autonomous Driving via Reinforcement Fine-Tuning

Autonomous Driving Systems (ADSs) continue to face safety-critical risks due to the inherent limitations in their design and performance capabilities. Online repair plays a crucial role in mitigating such limitations, ensuring the runtime safety and reliability of ADSs. Existing online repair solutions enforce ADS compliance by transforming unacceptable trajectories into acceptable ones based on predefined specifications, such as rule-based constraints or training datasets. However, these approaches often lack generalizability, adaptability and tend to be overly conservative, resulting in ineffective repairs that not only fail to mitigate safety risks sufficiently but also degrade the overall driving experience. To address this issue, we propose Adaptive Decision Repair (ADReFT), a novel and effective repair method that identifies safety-critical states through offline learning from failed tests and generates appropriate mitigation actions to improve ADS safety. Specifically, ADReFT incorporates a transformer-based model with two joint heads, State Monitor and Decision Adapter, designed to capture complex driving environment interactions to evaluate state safety severity and generate adaptive repair actions. Given the absence of oracles for state safety identification, we first pretrain ADReFT using supervised learning with coarse annotations, i.e., labeling states preceding violations as positive samples and others as negative samples. It establishes ADReFT's foundational capability to mitigate safety-critical violations, though it may result in somewhat conservative mitigation strategies. Therefore, we subsequently finetune ADReFT using reinforcement learning to improve its initial capability and generate more precise and contextually appropriate repair decisions. Our evaluation results illustrate that ADReFT achieves better repair performance.

cs.LG↗

arXiv2025

STCLocker: Deadlock Avoidance Testing for Autonomous Driving Systems

Autonomous Driving System (ADS) testing is essential to ensure the safety and reliability of autonomous vehicles (AVs) before deployment. However, existing techniques primarily focus on evaluating ADS functionalities in single-AV settings. As ADSs are increasingly deployed in multi-AV traffic, it becomes crucial to assess their cooperative performance, particularly regarding deadlocks, a fundamental coordination failure in which multiple AVs enter a circular waiting state indefinitely, resulting in motion planning failures. Despite its importance, the cooperative capability of ADSs to prevent deadlocks remains insufficiently underexplored. To address this gap, we propose the first dedicated Spatio-Temporal Conflict-Guided Deadlock Avoidance Testing technique, STCLocker, for generating DeadLock Scenarios (DLSs), where a group of AVs controlled by the ADS under test are in a circular wait state. STCLocker consists of three key components: Deadlock Oracle, Conflict Feedback, and Conflict-aware Scenario Generation. Deadlock Oracle provides a reliable black-box mechanism for detecting deadlock cycles among multiple AVs within a given scenario. Conflict Feedback and Conflict-aware Scenario Generation collaborate to actively guide AVs into simultaneous competition over spatial conflict resources (i.e., shared passing regions) and temporal competitive behaviors (i.e., reaching the conflict region at the same time), thereby increasing the effectiveness of generating conflict-prone deadlocks. We evaluate STCLocker on two types of ADSs: Roach, an end-to-end ADS, and OpenCDA, a module-based ADS supporting cooperative communication. Experimental results show that, on average, STCLocker generates more DLS than the best-performing baseline.

cs.SE↗

arXiv2025

Causality-aware Safety Testing for Autonomous Driving Systems

Simulation-based testing is essential for evaluating the safety of Autonomous Driving Systems (ADSs). Comprehensive evaluation requires testing across diverse scenarios that can trigger various types of violations under different conditions. While existing methods typically focus on individual diversity metrics, such as input scenarios, ADS-generated motion commands, and system violations, they often fail to capture the complex interrelationships among these elements. This oversight leads to gaps in testing coverage, potentially missing critical issues in the ADS under evaluation. However, quantifying these interrelationships presents a significant challenge. In this paper, we propose a novel causality-aware fuzzing technique, Causal-Fuzzer, to enable efficient and comprehensive testing of ADSs by exploring causally diverse scenarios. The core of Causal-Fuzzer is constructing a causal graph to model the interrelationships among the diversities of input scenarios, ADS motion commands, and system violations. Then the causal graph will guide the process of critical scenario generation. Specifically, Causal-Fuzzer proposes (1) a causality-based feedback mechanism that quantifies the combined diversity of test scenarios by assessing whether they activate new causal relationships, and (2) a causality-driven mutation strategy that prioritizes mutations on input scenario elements with higher causal impact on ego action changes and violation occurrence, rather than treating all elements equally. We evaluated Causal-Fuzzer on an industry-grade ADS Apollo, with a high-fidelity. Our empirical results demonstrate that Causal-Fuzzer significantly outperforms existing methods in (1) identifying a greater diversity of violations, (2) providing enhanced testing sufficiency with improved coverage of causal relationships, and (3) achieving greater efficiency in detecting the first critical scenarios.

cs.SE↗

arXiv2025

Moral Testing of Autonomous Driving Systems

Autonomous Driving System (ADS) testing plays a crucial role in their development, with the current focus primarily on functional and safety testing. However, evaluating the non-functional morality of ADSs, particularly their decision-making capabilities in unavoidable collision scenarios, is equally important to ensure the systems' trustworthiness and public acceptance. Unfortunately, testing ADS morality is nearly impossible due to the absence of universal moral principles. To address this challenge, this paper first extracts a set of moral meta-principles derived from existing moral experiments and well-established social science theories, aiming to capture widely recognized and common-sense moral values for ADSs. These meta-principles are then formalized as quantitative moral metamorphic relations, which act as the test oracle. Furthermore, we propose a metamorphic testing framework to systematically identify potential moral issues. Finally, we illustrate the implementation of the framework and present typical violation cases using the VIRES VTD simulator and its built-in ADS.

cs.SE↗

arXiv2025

Generation of entanglement between bright light fields via incoherent spontaneous emission

In contrast to the general argument that the spontaneous decay is intrinsically incoherent in nature and detrimental to quantum entanglement, here, we show that nearly perfect entanglement between two bright pump fields can be realized via spontaneous decay-induced destructive quantum interference in a closed double Lambda-type four-level atomic system with the energy separation of the excited doublet comparable to their decay rates. The high degree of bipartite entanglement results from the cancellation of spontaneous emission and subsequent elimination of the associated noise due to the destructive quantum interference between the two spontaneous emission pathways from the upper doublet to each of the two lower levels when the two strong pump fields are tuned to the particular frequencies where quantum interference takes place. This scheme is particularly suitable for the generation of entanglement between two bright light fields, and may find potential applications in realistic quantum information processing.

quant-ph↗

arXiv2025

Foundation Models for Autonomous Driving System: An Initial Roadmap

Recent advances in foundation models (FMs), including large language models (LLMs), vision-language models (VLMs), and world models, have opened new opportunities for autonomous driving systems (ADSs) in perception, reasoning, decision-making, and interaction. However, ADSs are safety-critical cyber-physical systems, and integrating FMs into them raises substantial software engineering challenges in data curation, system design, deployment, evaluation, and assurance. To clarify this rapidly evolving landscape, we present an initial roadmap, grounded in a structured literature review, for integrating FMs into autonomous driving across three dimensions: FM infrastructure, in-vehicle integration, and practical deployment. For each dimension, we summarize the state of the art, identify key challenges, and highlight open research opportunities. Based on this analysis, we outline research directions for building reliable, safe, and trustworthy FM-enabled ADSs.

cs.SE↗

arXiv2025

MoDitector: Module-Directed Testing for Autonomous Driving Systems

Testing Autonomous Driving Systems (ADS) is crucial for ensuring their safety, reliability, and performance. Despite numerous testing methods available that can generate diverse and challenging scenarios to uncover potential vulnerabilities, these methods often treat ADS as a black-box, primarily focusing on identifying system failures like collisions or near-misses without pinpointing the specific modules responsible for these failures. Understanding the root causes of failures is essential for effective debugging and subsequent system repair. We observed that existing methods also fall short in generating diverse failures that adequately test the distinct modules of an ADS, such as perception, prediction, planning and control. To bridge this gap, we introduce MoDitector, the first root-cause-aware testing method for ADS. Unlike previous approaches, MoDitector not only generates scenarios leading to collisions but also showing which specific module triggered the failure. This method targets specific modules, creating test scenarios that highlight the weaknesses of these given modules. Specifically, our approach involves designing module-specific oracles to ascertain module failures and employs a module-directed testing strategy that includes module-specific feedback, adaptive seed selection, and mutation. This strategy guides the generation of tests that effectively provoke module-specific failures. We evaluated MoDitector across four critical ADS modules and four testing scenarios. Our approach represents a significant innovation in ADS testing by focusing on identifying and rectifying module-specific errors within the system, moving beyond conventional black-box failure detection.

cs.SE↗

arXiv2024

DriveTester: A Unified Platform for Simulation-Based Autonomous Driving Testing

Simulation-based testing plays a critical role in evaluating the safety and reliability of autonomous driving systems (ADSs). However, one of the key challenges in ADS testing is the complexity of preparing and configuring simulation environments, particularly in terms of compatibility and stability between the simulator and the ADS. This complexity often results in researchers dedicating significant effort to customize their own environments, leading to disparities in development platforms and underlying systems. Consequently, reproducing and comparing these methodologies on a unified ADS testing platform becomes difficult. To address these challenges, we introduce DriveTester, a unified simulation-based testing platform built on Apollo, one of the most widely used open-source, industrial-level ADS platforms. DriveTester provides a consistent and reliable environment, integrates a lightweight traffic simulator, and incorporates various state-of-the-art ADS testing techniques. This enables researchers to efficiently develop, test, and compare their methods within a standardized platform, fostering reproducibility and comparison across different ADS testing approaches. The code is available: https://github.com/MingfeiCheng/DriveTester.

cs.SE↗

arXiv2024

LMM-enhanced Safety-Critical Scenario Generation for Autonomous Driving System Testing From Non-Accident Traffic Videos

Safety testing serves as the fundamental pillar for the development of autonomous driving systems (ADSs). To ensure the safety of ADSs, it is paramount to generate a diverse range of safety-critical test scenarios. While existing ADS practitioners primarily focus on reproducing real-world traffic accidents in simulation environments to create test scenarios, it's essential to highlight that many of these accidents do not directly result in safety violations for ADSs due to the differences between human driving and autonomous driving. More importantly, we observe that some accident-free real-world scenarios can not only lead to misbehaviors in ADSs but also be leveraged for the generation of ADS violations during simulation testing. Therefore, it is of significant importance to discover safety violations of ADSs from routine traffic scenarios (i.e., non-crash scenarios). We introduce LEADE, a novel methodology to achieve the above goal. It automatically generates abstract and concrete scenarios from real-traffic videos. Then it optimizes these scenarios to search for safety violations of the ADS in semantically consistent scenarios where human-driving worked safely. Specifically, LEADE enhances the ability of Large Multimodal Models (LMMs) to accurately construct abstract scenarios from traffic videos and generate concrete scenarios by multi-modal few-shot Chain of Thought (CoT). Based on them, LEADE assesses and increases the behavior differences between the ego vehicle and human-driving in semantic equivalent scenarios (here equivalent semantics means that each participant in test scenarios has the same behaviors as those observed in the original real traffic scenarios). We implement and evaluate LEADE on the industrial-grade Level-4 ADS, Apollo.

cs.SE↗